← Back to the carnage
ELEVENLABS

🟡 ElevenLabs endpoints decided to play slow-motion chess with your requests—Quality, Conversations, Integrations, and RAG all running at molasses speed. Engineers are investigating why their infrastructure suddenly developed commitment issues with actually responding to things.

⏰ 9h ago It's bad spotted via status_rss

// The official story

Multiple endpoints experiencing timeouts and latency

// Status page says

Status: Investigating We are investigating elevated latency and timeouts affecting multiple endpoints, including some Elevenagents endpoints. Some requests may be slow or fail. Our team is actively looking into the cause. Affected components Quality (Partial outage) Conversations (Partial outage) Integrations (Partial outage) RAG (Partial outage) Other API endpoints (Partial outage) Tele

🔗 Official status page (for the PR-approved version)

https://status.elevenlabs.io//incidents/01M4T91CTNSTQ93Q2Q31VQDBWH

Elevenlabs's Greatest Hits

🔴 ELEVENLABS 9h ago
🟡 ElevenLabs is speedrunning every engineer's nightmare: half their infrastructure decided latency is a feature, not a bug. Telephony, UI, Quality, Conversations, Integrations, and RAG are all throwing timeouts like they're going out of style. The team is "actively looking into it," which in corporate-to-English translates to "we have no idea what happened yet."
🟢 ELEVENLABS 5d ago
🟡 Your voice clones are now speaking in geological time. Dubbing latency and failures spiking while engineers frantically check if someone unplugged the main server. ElevenCreative is basically running on fumes and prayer. (Auto-resolved: no updates in 24h)
🟢 ELEVENLABS 5d ago
🟡 ElevenLabs Agent telephony is dropping SIP conversations like bad dates. Non-SIP calls still working, which is either lucky or means someone forgot to test the main thing. Engineers are investigating why their voice AI suddenly developed commitment issues. (Auto-resolved: no updates in 24h)
🟢 ELEVENLABS 5d ago
🟠 Routine maintenance decided to go rogue and nuke the infrastructure config, preventing new instances from even existing. Recovery required humans to actually touch keyboards. Music is back online after the manual CPR session. (Auto-resolved: no updates in 24h)